A Deep Convolutional Neural Network for the Early Detection of Heart Disease

Area of Science:

• Medical imaging analysis
• Artificial intelligence in healthcare
• Cardiology

Background:

• Heart disease is a leading cause of global mortality, necessitating advanced diagnostic tools.
• Traditional methods for heart disease detection have limitations, driving the need for improved technologies.
• Image classification, powered by machine learning and deep learning, offers enhanced precision in pattern recognition for medical diagnostics.

Purpose of the Study:

• To develop and evaluate a deep learning model for accurate heart disease detection.
• To leverage deep convolutional neural networks (DCNNs) for improved image classification in cardiac diagnostics.
• To assess the model's performance using standard metrics on a public heart disease dataset.

Main Methods:

• Utilized a deep convolutional neural network (DCNN) for image classification.
• Employed a public UCI heart disease dataset with 1050 patients and 14 attributes.
• Inputted a feature vector derived from patient data into the DCNN to classify healthy versus cardiac disease instances.

Main Results:

• The DCNN model achieved a validation accuracy of 91.7%.
• Performance was assessed using accuracy, precision, recall, and F1 measure.
• The model demonstrated significant effectiveness in distinguishing between healthy and cardiac disease cases.

Conclusions:

• The proposed deep learning approach using DCNNs is effective for heart disease detection.
• The model shows promise for real-world applications in identifying cardiac conditions.
• This study highlights the potential of advanced image classification techniques in improving diagnostic accuracy for heart disease.